jayn7/Z-Image-Turbo-GGUF
Quantization vs Tongyi-MAI/Z-Image-Turbo. jayn7/Z-Image-Turbo-GGUF is a GGUF quantization (Q8_0) of the same weights: 191 tensors match exactly and 120 within quantization error.
Tensors changed: Embeddings 0/7, other 0/66, Norms 0/136, MLP 0/102
2 derivatives checked
- emberstudios/PenisHelper: Adapter
- basibasigroup/lilly_lora.safetensors: Adapter